Expired65% confidenceEventExact time
有人在一台2020年发布、配备16GB内存的M1 Mac Mini上运行DeepSeek v4.1 Flash模型，每生成一个token需要约23秒
3
Sources
65%
Confidence
Short-term (~14 days)
Relevance
9/12/2026
First Seen
Valid until: 9/26/2026(expired)
Sources
Related Entities
Related Claims
Unverified27B稠密模型在24GB M4 Pro Mac mini上使用4-bit量化可以运行，速度约为11 tok/s76% similarVerifiedDeepSeek V4 Flash在OpenModel平台的速率限制为每分钟10次请求（10 RPM）和每分钟100K tokens（100K TPM）73% similarPartially VerifiedDS4 compresses the DeepSeek V4 Flash model from its original 284GB memory requirement down to 80-85GB, enabling it to run on a 128GB MacBook.72% similarUnverifiedDeepSeek V4 Flash是主打高吞吐的云端模型，推理速度可达约每秒140 tokens71% similarUnverified在16GB Mac Mini上Ornith 9B简单请求下生成速度约为16 tokens/秒71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/916414API
curl https://kongchang.com/api/v1/knowledge/claims/916414MCP
get_claim(id=916414)